The DOI matches its Crossref record; 30 of the 30 references it cites were found in a registry or an index.
PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentation
Open accessAbstract
Anomaly detection methods require high-quality features. In recent years, the anomaly detection community has attempted to obtain better features using advances in deep self-supervised feature learning. Surprisingly, a very promising direction, using pre-trained deep features, has been mostly overlooked. In this paper, we first empirically establish the perhaps expected, but unreported result, that combining pre-trained features with simple anomaly detection and segmentation methods convincingly outperforms, much more complex, state-of-the-art methods.In order to obtain further performance gains in anomaly detection, we adapt pre-trained features to the target distribution. Although transfer learning methods are well established in multi-class classification problems, the one-class classification (OCC) setting is not as well explored. It turns out that naive adaptation methods, which typically work well in supervised learning, often result in catastrophic collapse (feature deterioration) and reduce performance in OCC settings. A popular OCC method, DeepSVDD, advocates using specialized architectures, but this limits the adaptation performance gain. We propose two methods for combating collapse: i) a variant of early stopping that dynamically learns the stopping iteration ii) elastic regularization inspired by continual learning. Our method, PANDA, outperforms the state-of-the-art in the OCC, outlier exposure and anomaly segmentation settings by large margins1.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.74 · Cited by 24,513
Learning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,395
Algorithm AS 136: A K-Means Clustering Algorithm
Hartigan, J. A., & Wong, M. A. (1979) · Applied Statistics · doi:10.2307/2346830 · Cited by 14,523
A simple framework for contrastive learning of visual representations
Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020) · arXiv · doi:10.48550/arxiv.2002.05709 · Cited by 10,857
Overcoming catastrophic forgetting in neural networks
Kirkpatrick, J., Pascanu, R., Rabinowitz, N., Veness, J., Desjardins, G., Rusu, A. A., Milan, K., Quan, J., Ramalho, T., Grabska-Barwinska, A., et al. (2017) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1611835114 · Cited by 7,899
Robust principal component analysis?
Candès, E. J., Li, X., Ma, Y., & Wright, J. (2011) · Journal of the ACM · doi:10.1145/1970392.1970395 · Cited by 6,921
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
Xiao, H., Rasul, K., & Vollgraf, R. (2017) · arXiv · doi:10.48550/arxiv.1708.07747 · Cited by 6,108
Billion-scale similarity search with GPUs
Johnson, J., Douze, M., & Jegou, H. (2021) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2019.2921572 · Cited by 4,228
Billion-scale similarity search with GPUs
Johnson, J., Douze, M., & Jégou, H. (2017) · arXiv · doi:10.48550/arxiv.1702.08734 · Cited by 4,140
Caltech-UCSD Birds-200-2011 Dataset
Wah, C. (2024) · CaltechAUTHORS (California Institute of Technology) · doi:10.57702/i9oeewf6 · Cited by 3,525
Automated Flower Classification over a Large Number of Classes
Nilsback, M.-E., & Zisserman, A. (2008) · 2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing · doi:10.1109/icvgip.2008.47 · Cited by 3,442 · cited 2×
“Figure 1: An evaluation of SPADE on detecting anomalies between flowers with or without insects (taken from one category of 102 Category Flower Dataset [8]) and bird varieties (taken from Caltech-UCSD Birds 200) [14].”
MethodUnsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery
Schlegl, T., Seeböck, P., Waldstein, S. M., Schmidt-Erfurth, U., & Langs, G. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-59050-9_12 · Cited by 2,627
Object detection in optical remote sensing images: A survey and a new benchmark
Li, K., Wan, G., Cheng, G., Meng, L., & Han, J. (2020) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2019.11.023 · Cited by 2,317 · cited 4×
“3 on FMNIST, DIOR, WBC, MVTec suggest that out-of-domain pretrained features are better at anomaly detection than indomain self-supervised features.”
MethodInfluentialMVTec AD — A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection
Bergmann, P., Fauser, M., Sattlegger, D., & Steger, C. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00982 · Cited by 2,203 · cited 2×
“[2] evaluated both a ADGAN and autoencoder approaches on MVTec dataset [2] finding complementary strengths.”
MethodSupport Vector Method for Novelty Detection
Schölkopf, B., Williamson, R. C., Smola, A. J., Shawe-Taylor, J. S., & Platt, J. C. (1999) · Cited by 2,040
80 Million Tiny Images: A Large Data Set for Nonparametric Object and Scene Recognition
Torralba, A., Fergus, R., & Freeman, W. T. (2008) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2008.128 · Cited by 1,921
Jolliffe, I. (2014) · Wiley StatsRef: Statistics Reference Online · doi:10.1002/9781118445112.stat06472 · Cited by 1,221
Uninformed Students: Student-Teacher Anomaly Detection With Discriminative Latent Embeddings
Bergmann, P., Fauser, M., Sattlegger, D., & Steger, C. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00424 · Cited by 990
A Geometric Framework for Unsupervised Anomaly Detection: Detecting Intrusions in Unlabeled Data
Eskin, E., Arnold, A., Prerau, M., Portnoy, L., & Stolfo, S. (2002) · Advances in Information Security · doi:10.1007/978-1-4615-0953-0_4 · Cited by 683
Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty
Hendrycks, D., Mazeika, M., Kadavath, S., & Song, D. (2019) · arXiv · doi:10.48550/arxiv.1906.12340 · Cited by 634
Asirra: A captcha that exploits interest-aligned manual image categorization
Elson, J., Douceur, J. R., Howell, J., & Saul, J. (2007) · Cited by 479
Using Pre-Training Can Improve Model Robustness and Uncertainty
Hendrycks, D., Lee, K., & Mazeika, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.09960 · Cited by 408
Learning Deep Features for One-Class Classification
Perera, P., & Patel, V. M. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2917862 · Cited by 399
Deep Anomaly Detection Using Geometric Transformations
Golan, I., & El‐Yaniv, R. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.10917 · Cited by 372
Anomaly Detection in Nanofibrous Materials by CNN-Based Self-Similarity
Napoletano, P., Piccoli, F., & Schettini, R. (2018) · Sensors · doi:10.3390/s18010209 · Cited by 285
Outlier Detection with Kernel Density Functions
Latecki, L. J., Lazarevic, A., & Pokrajac, D. (2007) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-73499-4_6 · Cited by 273
What makes ImageNet good for transfer learning?
Huh, M., Agrawal, P., & Efros, A. A. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1608.08614 · Cited by 266
Fast and robust segmentation of white blood cell images by self-supervised learning
Zheng, X., Wang, Y., Wang, G., & Liu, J. (2018) · Micron · doi:10.1016/j.micron.2018.01.010 · Cited by 248
Deep Nearest Neighbor Anomaly DetectionPreprint
Bergman, L., Cohen, N., & Hoshen, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.10445 · Cited by 247
Self-citationAttention Guided Anomaly Localization in Images
Venkataramanan, S., Peng, K.-C., Singh, R. V., & Mahalanobis, A. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58520-4_29 · Cited by 247
Cited by
Anomaly Detection via Reverse Distillation from One-Class Embedding
Deng, H., & Li, X. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00951 · Cited by 892
Surface Defect Detection Methods for Industrial Products: A Review
Chen, Y., Ding, Y., Zhao, F., Zhang, E., Wu, Z., & Shao, L. (2021) · Applied Sciences · doi:10.3390/app11167657 · Cited by 457
Deep Industrial Image Anomaly Detection: A Survey
Liu, J., Xie, G., Wang, J., Li, S., Wang, C., Zheng, F., & Jin, Y. (2024) · Machine Intelligence Research · doi:10.1007/s11633-023-1459-z · Cited by 463
“PANDA [25] examines the migration method of pre-trained features and introduces the early stopping mechanism to the OCC problem.”
InfluentialGAN-based anomaly detection: A review
Xia, X., Pan, X., Li, N., He, X., Ma, L., Zhang, X., & Ding, N. (2022) · Neurocomputing · doi:10.1016/j.neucom.2021.12.093 · Cited by 392
FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows
Yu, J., Zheng, Y., Wang, X., Li, W., Wu, Y., Zhao, R., & Wu, L. (2021) · arXiv · doi:10.48550/arxiv.2111.07677 · Cited by 210
Metadata
- Authors
- Reiss, T., Cohen, N., Bergman, L., & Hoshen, Y.
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 2805-2813
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3157224024
- Cited by
- 281
- References
- 30
- FWCI
- 24.43
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.